You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Maryann Xue (JIRA)" <ji...@apache.org> on 2018/06/29 20:11:00 UTC
[jira] [Updated] (SPARK-24696) ColumnPruning rule fails to remove
extra Project
[ https://issues.apache.org/jira/browse/SPARK-24696?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Maryann Xue updated SPARK-24696:
--------------------------------
Description:
The following test case would cause a "max iterations reached" error, i.e., an infinite loop in the optimizer.
{code}
test("optimization infinite loop") {
withTempDir { dir =>
val path = dir.getCanonicalPath
import testImplicits._
Seq((3, "a")).toDF("id", "value").write.format("parquet").mode("overwrite").save(path)
import org.apache.spark.sql.functions.udf
val filterIt = udf((value: Int) => value > 0).asNondeterministic
spark.read.load(path)
.where(filterIt('id))
.where('id < 0)
.select('id)
.collect
}
}
{code}
Error message:
{code}
Max iterations (100) reached for batch Operator Optimization before Inferring Filters, tree:
Filter (id#11 < 0)
+- Project [id#11]
+- Filter if (isnull(id#11)) null else UDF(id#11)
+- Relation[id#11,value#12] parquet
org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Max iterations (100) reached for batch Operator Optimization before Inferring Filters, tree:
Filter (id#11 < 0)
+- Project [id#11]
+- Filter if (isnull(id#11)) null else UDF(id#11)
+- Relation[id#11,value#12] parquet
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:117)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
at org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:66)
at org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:66)
at org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:72)
at org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:68)
at org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:77)
at org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:77)
at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3286)
at org.apache.spark.sql.Dataset.collect(Dataset.scala:2745)
at org.apache.spark.sql.DataFrameSuite$$anonfun$94$$anonfun$apply$mcV$sp$199.apply(DataFrameSuite.scala:2343)
at org.apache.spark.sql.DataFrameSuite$$anonfun$94$$anonfun$apply$mcV$sp$199.apply(DataFrameSuite.scala:2333)
at org.apache.spark.sql.test.SQLTestUtilsBase$class.withTempDir(SQLTestUtils.scala:215)
at org.apache.spark.sql.DataFrameSuite.withTempDir(DataFrameSuite.scala:43)
at org.apache.spark.sql.DataFrameSuite$$anonfun$94.apply$mcV$sp(DataFrameSuite.scala:2333)
at org.apache.spark.sql.DataFrameSuite$$anonfun$94.apply(DataFrameSuite.scala:2333)
at org.apache.spark.sql.DataFrameSuite$$anonfun$94.apply(DataFrameSuite.scala:2333)
at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
at org.scalatest.Transformer.apply(Transformer.scala:22)
at org.scalatest.Transformer.apply(Transformer.scala:20)
at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:186)
at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:103)
at org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:183)
at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196)
at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196)
at org.scalatest.SuperEngine.runTestImpl(Engine.scala:289)
at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:196)
at org.apache.spark.sql.DataFrameSuite.org$scalatest$BeforeAndAfterEach$$super$runTest(DataFrameSuite.scala:43)
at org.scalatest.BeforeAndAfterEach$class.runTest(BeforeAndAfterEach.scala:221)
at org.apache.spark.sql.DataFrameSuite.runTest(DataFrameSuite.scala:43)
at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229)
at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229)
at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:396)
at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:384)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384)
at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:379)
at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:461)
at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:229)
at org.scalatest.FunSuite.runTests(FunSuite.scala:1560)
at org.scalatest.Suite$class.run(Suite.scala:1147)
at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1560)
at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233)
at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233)
at org.scalatest.SuperEngine.runImpl(Engine.scala:521)
at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:233)
at org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterAll$$super$run(SparkFunSuite.scala:52)
at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:213)
at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:210)
at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:52)
at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:45)
at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1340)
at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1334)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:1334)
at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1011)
at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1010)
at org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:1500)
at org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1010)
at org.scalatest.tools.Runner$.run(Runner.scala:850)
at org.scalatest.tools.Runner.run(Runner.scala)
at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.runScalaTest2(ScalaTestRunner.java:131)
at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.main(ScalaTestRunner.java:28)
{code}
was:
{code}
test("optimization infinite loop") {
withTempDir { dir =>
val path = dir.getCanonicalPath
import testImplicits._
Seq((3, "a")).toDF("id", "value").write.format("parquet").mode("overwrite").save(path)
import org.apache.spark.sql.functions.udf
val filterIt = udf((value: Int) => value > 0).asNondeterministic
spark.read.load(path)
.where(filterIt('id))
.where('id < 0)
.select('id)
.collect
}
}
{code}
> ColumnPruning rule fails to remove extra Project
> ------------------------------------------------
>
> Key: SPARK-24696
> URL: https://issues.apache.org/jira/browse/SPARK-24696
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 2.3.1
> Reporter: Xiao Li
> Assignee: Maryann Xue
> Priority: Major
>
> The following test case would cause a "max iterations reached" error, i.e., an infinite loop in the optimizer.
> {code}
> test("optimization infinite loop") {
> withTempDir { dir =>
> val path = dir.getCanonicalPath
> import testImplicits._
> Seq((3, "a")).toDF("id", "value").write.format("parquet").mode("overwrite").save(path)
> import org.apache.spark.sql.functions.udf
> val filterIt = udf((value: Int) => value > 0).asNondeterministic
> spark.read.load(path)
> .where(filterIt('id))
> .where('id < 0)
> .select('id)
> .collect
> }
> }
> {code}
> Error message:
> {code}
> Max iterations (100) reached for batch Operator Optimization before Inferring Filters, tree:
> Filter (id#11 < 0)
> +- Project [id#11]
> +- Filter if (isnull(id#11)) null else UDF(id#11)
> +- Relation[id#11,value#12] parquet
> org.apache.spark.sql.catalyst.errors.package$TreeNodeException: Max iterations (100) reached for batch Operator Optimization before Inferring Filters, tree:
> Filter (id#11 < 0)
> +- Project [id#11]
> +- Filter if (isnull(id#11)) null else UDF(id#11)
> +- Relation[id#11,value#12] parquet
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:117)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
> at scala.collection.immutable.List.foreach(List.scala:392)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
> at org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:66)
> at org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:66)
> at org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:72)
> at org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:68)
> at org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:77)
> at org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:77)
> at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3286)
> at org.apache.spark.sql.Dataset.collect(Dataset.scala:2745)
> at org.apache.spark.sql.DataFrameSuite$$anonfun$94$$anonfun$apply$mcV$sp$199.apply(DataFrameSuite.scala:2343)
> at org.apache.spark.sql.DataFrameSuite$$anonfun$94$$anonfun$apply$mcV$sp$199.apply(DataFrameSuite.scala:2333)
> at org.apache.spark.sql.test.SQLTestUtilsBase$class.withTempDir(SQLTestUtils.scala:215)
> at org.apache.spark.sql.DataFrameSuite.withTempDir(DataFrameSuite.scala:43)
> at org.apache.spark.sql.DataFrameSuite$$anonfun$94.apply$mcV$sp(DataFrameSuite.scala:2333)
> at org.apache.spark.sql.DataFrameSuite$$anonfun$94.apply(DataFrameSuite.scala:2333)
> at org.apache.spark.sql.DataFrameSuite$$anonfun$94.apply(DataFrameSuite.scala:2333)
> at org.scalatest.OutcomeOf$class.outcomeOf(OutcomeOf.scala:85)
> at org.scalatest.OutcomeOf$.outcomeOf(OutcomeOf.scala:104)
> at org.scalatest.Transformer.apply(Transformer.scala:22)
> at org.scalatest.Transformer.apply(Transformer.scala:20)
> at org.scalatest.FunSuiteLike$$anon$1.apply(FunSuiteLike.scala:186)
> at org.apache.spark.SparkFunSuite.withFixture(SparkFunSuite.scala:103)
> at org.scalatest.FunSuiteLike$class.invokeWithFixture$1(FunSuiteLike.scala:183)
> at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196)
> at org.scalatest.FunSuiteLike$$anonfun$runTest$1.apply(FunSuiteLike.scala:196)
> at org.scalatest.SuperEngine.runTestImpl(Engine.scala:289)
> at org.scalatest.FunSuiteLike$class.runTest(FunSuiteLike.scala:196)
> at org.apache.spark.sql.DataFrameSuite.org$scalatest$BeforeAndAfterEach$$super$runTest(DataFrameSuite.scala:43)
> at org.scalatest.BeforeAndAfterEach$class.runTest(BeforeAndAfterEach.scala:221)
> at org.apache.spark.sql.DataFrameSuite.runTest(DataFrameSuite.scala:43)
> at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229)
> at org.scalatest.FunSuiteLike$$anonfun$runTests$1.apply(FunSuiteLike.scala:229)
> at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:396)
> at org.scalatest.SuperEngine$$anonfun$traverseSubNodes$1$1.apply(Engine.scala:384)
> at scala.collection.immutable.List.foreach(List.scala:392)
> at org.scalatest.SuperEngine.traverseSubNodes$1(Engine.scala:384)
> at org.scalatest.SuperEngine.org$scalatest$SuperEngine$$runTestsInBranch(Engine.scala:379)
> at org.scalatest.SuperEngine.runTestsImpl(Engine.scala:461)
> at org.scalatest.FunSuiteLike$class.runTests(FunSuiteLike.scala:229)
> at org.scalatest.FunSuite.runTests(FunSuite.scala:1560)
> at org.scalatest.Suite$class.run(Suite.scala:1147)
> at org.scalatest.FunSuite.org$scalatest$FunSuiteLike$$super$run(FunSuite.scala:1560)
> at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233)
> at org.scalatest.FunSuiteLike$$anonfun$run$1.apply(FunSuiteLike.scala:233)
> at org.scalatest.SuperEngine.runImpl(Engine.scala:521)
> at org.scalatest.FunSuiteLike$class.run(FunSuiteLike.scala:233)
> at org.apache.spark.SparkFunSuite.org$scalatest$BeforeAndAfterAll$$super$run(SparkFunSuite.scala:52)
> at org.scalatest.BeforeAndAfterAll$class.liftedTree1$1(BeforeAndAfterAll.scala:213)
> at org.scalatest.BeforeAndAfterAll$class.run(BeforeAndAfterAll.scala:210)
> at org.apache.spark.SparkFunSuite.run(SparkFunSuite.scala:52)
> at org.scalatest.tools.SuiteRunner.run(SuiteRunner.scala:45)
> at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1340)
> at org.scalatest.tools.Runner$$anonfun$doRunRunRunDaDoRunRun$1.apply(Runner.scala:1334)
> at scala.collection.immutable.List.foreach(List.scala:392)
> at org.scalatest.tools.Runner$.doRunRunRunDaDoRunRun(Runner.scala:1334)
> at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1011)
> at org.scalatest.tools.Runner$$anonfun$runOptionallyWithPassFailReporter$2.apply(Runner.scala:1010)
> at org.scalatest.tools.Runner$.withClassLoaderAndDispatchReporter(Runner.scala:1500)
> at org.scalatest.tools.Runner$.runOptionallyWithPassFailReporter(Runner.scala:1010)
> at org.scalatest.tools.Runner$.run(Runner.scala:850)
> at org.scalatest.tools.Runner.run(Runner.scala)
> at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.runScalaTest2(ScalaTestRunner.java:131)
> at org.jetbrains.plugins.scala.testingSupport.scalaTest.ScalaTestRunner.main(ScalaTestRunner.java:28)
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org